Теорія ймовірності і математична статистика (укр.)Probability theory and mathematical statistics (en.)

Analysis of the correlations examined in chapter 5 is often performed with the aid of multiple-parameter linear regression methods. Let us examine some of the obtained results, which have been used for developing practical methods of urban air pollution forecasting.

Statistical methods of air pollution forecasting

Received: 24 April 2020 Accepted: 10 June 2020 Much attention is paid to problem of reducing losses of electric energy in electric power industry of many countries, especially in Ukraine. Distribution networks of industrial enterprises in Ukraine are characterized by two voltage levels 0.4 and 10 kV. Active power factor of industrial power consumers is determined by nature of process and many electrical installations have low cosφ values. Significant flows of reactive power and, as a result, additional irrational losses of electric energy take place in the distribution networks of enterprises as a result. Purpose of this article is to improve methodology of design justification for selection of main elements of internal power supply system of industrial enterprise to obtain rational compensation of reactive power in distribution network of enterprise. Existing methodology for designing a reactive power compensation system involves use of averaged indicators of unit cost of power equipment (transformers, compensating devices) and is based on assumption of linear nature of dependence of these indicators on power of equipment. Study of these dependencies for equipment of number of manufacturers showed their nonlinear character that is not formalized. Article proposes methodology for selecting number and power of compensating devices at same time as power transformers of workshop substations according to criterion of minimum annual reduced costs for these power supply system elements at design stage of power supply system. Proposed method takes into account real cost of power equipment, which can be used in reactive power compensation system at designed enterprise and provides choice of option that meets technical requirements of regulatory documents and has a minimum annual cost.

/pdf/methodology-calculation-for-reactive-power-compensation-in-3cdbbmx6e1.pdf

Methodology Calculation for Reactive Power Compensation in Industrial Enterprises

/pdf/regressive-methods-of-prognostication-of-the-load-graph-of-476i29sv6g.pdf

Regressive methods of prognostication of the load-graph of electrical equipment

An increase in the number of alternative energy sources, in particular solar power stations in the generation structure of the modern energy systems, makes it difficult to control such energy systems due to the inconsistency in the amount of electricity production that depends on external factors. It also leads to an increase in risks when concluding electricity supply agreements in a modern energy market. This problem may be solved by forecasting electricity by modern means, such as neural networks. In this context, due to the flexibility and nonlinearity of neural networks there is no need for source data that directly affects the generation value, and there is a possibility of using indirect data available to most alternative energy producers. This has resulted in the creation of the solution based on neural networks that allows forecasting energy production using solar panels with high accuracy on the basis of conventional meteorological data.

Forecasting of Electricity Generation by Solar Panels Using Neural Networks with Incomplete Initial Data

The high cost of electric power, as well as the considerable length and branching of electrical networks, necessitate reduce electric power consumption, and losses in electrical networks. One of solutions of this problem is optimizing the reactive power mode. Reducing the reactive power factor at the point of common coupling (PCC) to the economic level established by the power system is not taking into account that in a complex network, power flows with a non-optimal arrangement of compensating devices and improper determination of their power can reach large values, that resulting in an increase in losses in the network. A program has been developed that implements prediction algorithms using neural networks, as well as optimizing the reactive power mode.

Victor Sychenko

Papers

Development of Methods for Optimizing Reactive Power Modes Based on Neural Network Technologies